{"id":"https://openalex.org/W3139059142","doi":"https://doi.org/10.1109/bigdata50022.2020.9377986","title":"First Steps Toward Synthetic Sample Generation for Machine Learning Based Flare Forecasting","display_name":"First Steps Toward Synthetic Sample Generation for Machine Learning Based Flare Forecasting","publication_year":2020,"publication_date":"2020-12-10","ids":{"openalex":"https://openalex.org/W3139059142","doi":"https://doi.org/10.1109/bigdata50022.2020.9377986","mag":"3139059142"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata50022.2020.9377986","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377986","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022286188","display_name":"Maxwell Hostetter","orcid":null},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Maxwell Hostetter","raw_affiliation_strings":["Department of Computer Science, Georgia State University, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Georgia State University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I181565077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009847987","display_name":"Rafal A. Angryk","orcid":"https://orcid.org/0000-0001-9598-8207"},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rafal A. Angryk","raw_affiliation_strings":["Department of Computer Science, Georgia State University, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Georgia State University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I181565077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5022286188"],"corresponding_institution_ids":["https://openalex.org/I181565077"],"apc_list":null,"apc_paid":null,"fwci":0.1326,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58490023,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4208","last_page":"4217"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13429","display_name":"Electricity Theft Detection Techniques","score":0.963699996471405,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13693","display_name":"Smart Systems and Machine Learning","score":0.9599000215530396,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.9842303991317749},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6905449628829956},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.629508376121521},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6059876084327698},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.591256856918335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5525781512260437},{"id":"https://openalex.org/keywords/solar-flare","display_name":"Solar flare","score":0.4838930070400238},{"id":"https://openalex.org/keywords/flare","display_name":"Flare","score":0.416319876909256},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3510088324546814},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10458409786224365},{"id":"https://openalex.org/keywords/astrophysics","display_name":"Astrophysics","score":0.09508925676345825},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09281522035598755},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.07277822494506836}],"concepts":[{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.9842303991317749},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6905449628829956},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.629508376121521},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6059876084327698},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.591256856918335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5525781512260437},{"id":"https://openalex.org/C185001636","wikidata":"https://www.wikidata.org/wiki/Q119830","display_name":"Solar flare","level":2,"score":0.4838930070400238},{"id":"https://openalex.org/C2779588948","wikidata":"https://www.wikidata.org/wiki/Q628261","display_name":"Flare","level":2,"score":0.416319876909256},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3510088324546814},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10458409786224365},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.09508925676345825},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09281522035598755},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.07277822494506836},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata50022.2020.9377986","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377986","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332169","display_name":"Directorate for Computer and Information Science and Engineering","ror":"https://ror.org/025kzpk63"},{"id":"https://openalex.org/F4320337563","display_name":"Division of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1541033774","https://openalex.org/W1588282782","https://openalex.org/W1591261915","https://openalex.org/W2033706575","https://openalex.org/W2053724458","https://openalex.org/W2076272581","https://openalex.org/W2093586470","https://openalex.org/W2099471712","https://openalex.org/W2104167780","https://openalex.org/W2106479238","https://openalex.org/W2111078819","https://openalex.org/W2118978333","https://openalex.org/W2122755404","https://openalex.org/W2148143831","https://openalex.org/W2297432279","https://openalex.org/W2783270368","https://openalex.org/W2954809622","https://openalex.org/W2969674096","https://openalex.org/W2995887271","https://openalex.org/W3007210650","https://openalex.org/W3010992329","https://openalex.org/W3041430681","https://openalex.org/W3099506237","https://openalex.org/W3100277955","https://openalex.org/W3102688741","https://openalex.org/W3102780218","https://openalex.org/W4320013936","https://openalex.org/W6635474240","https://openalex.org/W6664464457","https://openalex.org/W6867866341","https://openalex.org/W7053126446"],"related_works":["https://openalex.org/W2104143565","https://openalex.org/W1529285236","https://openalex.org/W4391503899","https://openalex.org/W2027190773","https://openalex.org/W1976886998","https://openalex.org/W3174659840","https://openalex.org/W1649705128","https://openalex.org/W161133865","https://openalex.org/W1546351615","https://openalex.org/W2033757218"],"abstract_inverted_index":{"The":[0],"imbalanced":[1,26,33],"class":[2],"problem":[3],"is":[4,35],"intrinsic":[5],"to":[6,36,44,59],"solar":[7,76,136],"flare":[8,77,137],"forecasting,":[9],"as":[10],"are":[11,21],"other":[12,66],"issues":[13],"we":[14,68],"find":[15],"in":[16,61,75],"data-driven":[17],"forecasting":[18],"problems":[19,60],"that":[20,126],"often":[22],"hidden":[23],"within":[24],"an":[25],"dataset.":[27,122],"One":[28],"method":[29],"of":[30,48,83],"dealing":[31],"with":[32],"data":[34,39,109],"balance":[37],"the":[38,49,112],"by":[40,111],"using":[41],"synthetic":[42,46,53,84,101,127],"oversampling":[43,54,102,128],"create":[45],"examples":[47],"minority":[50],"class.":[51],"Though":[52],"techniques":[55,103],"have":[56,69],"been":[57],"applied":[58],"medicine,":[62],"finance,":[63],"security,":[64],"and":[65,91],"areas,":[67],"not":[70],"seen":[71],"these":[72],"approaches":[73],"used":[74],"forecasting.":[78,138],"We":[79,97,106],"investigate":[80],"two":[81],"methods":[82],"oversampling,":[85],"Rapidly":[86],"Converging":[87],"Gibbs":[88],"Sampler":[89],"(RACOG)":[90],"Synthetic":[92],"Minority":[93],"Oversampling":[94],"Technique":[95],"(SMOTE).":[96],"devise":[98],"three":[99],"naive":[100],"for":[104,116,132],"compar-ison.":[105],"rely":[107],"on":[108],"provided":[110],"Space":[113],"Weather":[114],"ANalytics":[115],"Solar":[117],"Flares":[118],"(SWAN-":[119],"SF)":[120],"benchmark":[121],"Our":[123],"results":[124],"indicate":[125],"can":[129],"be":[130],"effective":[131],"machine":[133],"learning":[134],"based":[135]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}